# Doubao Seed Realtime 1.0

> ByteDance's full-duplex audio and video call model that watches the camera or screen, listens and talks at the same time, and can speak up on its own.

Agent resources: the index of everything machine-readable is https://www.ohmygpt.com/llms.txt; the integration skill (endpoints, auth, SDK and coding-tool setup) is https://www.ohmygpt.com/skill.md.

- Model ID: `bytedance/doubao-seed-realtime-1.0`
- Live status and providers as JSON, no key needed: https://api.ohmygpt.com/v1/models/bytedance/doubao-seed-realtime-1.0
- Released: 2026-11-19
- Context: 64K tokens
- Max output: 64K tokens
- Input: audio, image, video, text; output: audio, text

## Prices (USD)

| Item | Price | Unit |
| --- | --- | --- |
| Video | $0.000536 | per second |
| Transcription | $0.000536 | per second |

## Providers

Without a prefix each request goes to the best-priced healthy provider. To pin one, send the model as `<provider>:bytedance/doubao-seed-realtime-1.0`.

| Provider | Pinned model ID | Location | Input | Output | Trains on your data |
| --- | --- | --- | --- | --- | --- |
| ByteDance (Doubao Speech) | `doubao_speech:bytedance/doubao-seed-realtime-1.0` | China | — | — | — |

Web page: https://www.ohmygpt.com/models/bytedance/doubao-seed-realtime-1.0
